Hnimrama/atom p2 - #381
Open
hnimra-amd wants to merge 9 commits into
Open
Conversation
cijohnson
reviewed
Sep 1, 2026
| @@ -0,0 +1,240 @@ | |||
| .. meta:: | |||
Collaborator
There was a problem hiding this comment.
This file is not needed, there is already a https://github.com/ROCm/cvs/blob/main/docs/how-to/test-suites/inference/atom.rst in main branch
cijohnson
reviewed
Sep 1, 2026
| @@ -0,0 +1,78 @@ | |||
| .. meta:: | |||
Collaborator
There was a problem hiding this comment.
this file doesn't exits in main baranch
Contributor
Author
There was a problem hiding this comment.
I was still rebasing the branch so it had older stuff
cijohnson
requested changes
Sep 1, 2026
cijohnson
left a comment
cijohnson
left a comment
Collaborator
There was a problem hiding this comment.
I think you need to rebase your branch from main
cijohnson
reviewed
Sep 1, 2026
| @@ -0,0 +1,46 @@ | |||
| { | |||
Collaborator
There was a problem hiding this comment.
i think the _threshold.json cannot have mi3xx, as the threshold will change for each platform, so we need it to be
mi300 or mi325 (which ever platform you tested), pleas commit only thresholds for the platform your tested
CC: @atnair-amd , @amd-droy
cijohnson
requested changes
Sep 1, 2026
cijohnson
reviewed
Sep 1, 2026
Collaborator
There was a problem hiding this comment.
Similarly lets not commit the config file for mi35x_ if we have not tested in the mi35x platforms
hnimra-amd
marked this pull request as draft
September 1, 2026 20:59
hnimra-amd
force-pushed
the
hnimrama/atom_p2
branch
from
September 1, 2026 21:00
503e513 to
c11c2a1
Compare
…s only. Use platform-specific mi325x stems (lab-validated on MI325X), aligned threshold cell keys (PP=, bare metrics), and Sphinx docs without local inference markdown drafts.
hnimra-amd
force-pushed
the
hnimrama/atom_p2
branch
from
September 1, 2026 21:11
bfc0016 to
b096c00
Compare
Rename ATOM variant JSON files to mi3xx family stems while keeping platform-specific mi325x threshold files. Run ruff format on atom_config_loader and its unit tests to satisfy CI fmt-check.
hnimra-amd
marked this pull request as ready for review
September 1, 2026 21:34
Drop redundant gpu_arch from shipped mi3xx configs; load_variant derives it from the {gpu}_atom_* stem with optional JSON override.
Extend schema v2 stems with perf, vllm, and sglang profiles including acc_warmup and accuracy suites, rename and align mi325x threshold files per profile, and update the config loader, unit tests, and how-to docs.
Export METRIC_UNITS for the atom run-deck profile, register --config_profile on the pytest CLI, and fix the invalid BrokenPipeError filterwarnings entry for pytest 9.
hnimra-amd
force-pushed
the
hnimrama/atom_p2
branch
from
September 2, 2026 18:50
8e3088a to
433bec1
Compare
MiniMax and MiMo need block-size 128 and compile-disabled startup flags on openai_server; atom_orch now defaults enforce-eager for native atom driver. Remove GLM 5.1 ATOM variant files that fail on rc3 in lab.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.